111 results
Image generation for DeepSeek Harness: a generate_image tool with pluggable providers — the FAL queue, any OpenAI-compatible images API, or a ChatGPT/Grok subscription with no API key at all. The picture is shown inline in the conversation; the model rece
Zero-config local vision and realtime audio routing for DeepSeek Harness
DSH 自定义厂商适配器：为 OpenAI 兼容的私有/公司模型端点提供可选的 HTTP(S) 代理转发，并在设置页提供可视化配置表单。
DeepSeek Harness plugin: content-routing LLM adapter. Text-only requests go to DeepSeek; requests containing images go to a user-configurable OpenAI-compatible vision provider. Read_image works natively for text-only models.
Give DeepSeek Harness eyes: a vision_analyze tool that sends an image (local path or URL) to an OpenAI-compatible vision model and returns a text description.
Bring ChatGPT-like image generation to DeepSeek Harness — Gemini, OpenAI, Seedream, DashScope, local ComfyUI & more.
Per-model reasoning effort declarations for GPT, Gemini and OpenAI-compatible providers in DeepSeek Harness
Cross-provider second-opinion advisor for dsh. v2 (simple-extensible-configurable-stable): DEFAULT ROUTE = official DeepSeek (deepseek-official/deepseek-v4-flash); model param optional everywhere; one-page visual settings panel; honest audit trail. Scout mode = official + live web_search. OpenAI-compatible endpoint + consult tool + DSH_MODEL rerouting.
Voice input for DeepSeek Harness: dictation chunked by pauses and voice messages, each with its own provider fallback chain (Deepgram, Groq, HuggingFace, local whisper.cpp, plus any OpenAI-compatible API of your own).
DSH 视觉桥接插件：复用 DSH Provider 或 OpenAI 兼容直连，支持可视化配置与图片粘贴
DSH plugin: speech-to-text input via microphone or file upload, transcribed through an OpenAI-compatible /v1/audio/transcriptions endpoint.
DeepSeek Harness plugin: one compat_probe tool that probes an OpenAI-compatible base URL and returns a structured protocol card
DeepSeek Harness bundle for MotoMoto's OpenAI-compatible endpoint: a pi-ai provider route plus a status card in Settings - Plugins.
DSH plugin: manages the Windows llama-server.exe model lifecycle (start / stop / switch / recover) behind a stable OpenAI-compatible gateway, with graceful Ctrl+C shutdown that actually frees VRAM.
WorkBuddy (workbuddy.ai / codebuddy.cn) subscription quota as a DSH model provider: supervises the local OpenAI-compatible gateway and exposes it as a settings page.